22 references to Cl100kBase
Microsoft.ML.Tokenizers (22)
Model\TiktokenTokenizer.cs (22)
1053( "gpt-4-", ModelEncoding.Cl100kBase ), // e.g., gpt-4-0314, etc., plus gpt-4-32k
1054( "gpt-3.5-", ModelEncoding.Cl100kBase ), // e.g, gpt-3.5-turbo-0301, -0401, etc.
1055( "gpt-35-", ModelEncoding.Cl100kBase ), // Azure deployment name
1060( "ft:gpt-4", ModelEncoding.Cl100kBase ),
1061( "ft:gpt-3.5-turbo", ModelEncoding.Cl100kBase ),
1062( "ft:davinci-002", ModelEncoding.Cl100kBase ),
1063( "ft:babbage-002", ModelEncoding.Cl100kBase ),
1079{ "gpt-4", ModelEncoding.Cl100kBase },
1080{ "gpt-3.5-turbo", ModelEncoding.Cl100kBase },
1081{ "gpt-3.5", ModelEncoding.Cl100kBase },
1082{ "gpt-3.5-turbo-16k", ModelEncoding.Cl100kBase },
1083{ "gpt-35", ModelEncoding.Cl100kBase }, // Azure deployment name
1084{ "gpt-35-turbo", ModelEncoding.Cl100kBase }, // Azure deployment name
1085{ "gpt-35-turbo-16k", ModelEncoding.Cl100kBase }, // Azure deployment name
1088{ "davinci-002", ModelEncoding.Cl100kBase },
1089{ "babbage-002", ModelEncoding.Cl100kBase },
1093{ "text-embedding-ada-002", ModelEncoding.Cl100kBase },
1094{ "text-embedding-3-small", ModelEncoding.Cl100kBase },
1095{ "text-embedding-3-large", ModelEncoding.Cl100kBase },
1140{ Phi4ModelName, ModelEncoding.Cl100kBase },
1197case ModelEncoding.Cl100kBase:
1537modelEncoding = ModelEncoding.Cl100kBase;